fix(2): F2-3 systemic — harness.browser.goto_with_retry; applied to all install overlays
Phase 2 lesson from F2-3 (n8n install Playwright flake on net::ERR_NETWORK_CHANGED): every install overlay that does page.goto needs the same try/except PlaywrightError + status retry. Centralize in runner/harness/browser.py::goto_with_retry; apply to ALL install overlays. - runner/harness/browser.py: shared helper. Polls page.goto until status in accept_statuses; catches PlaywrightError (net::ERR_*) as a retryable signal, not a failure. Raises AssertionError with last_status + last_err diagnostic only on deadline expiry. - tests/custom-html/test_install.py: now uses goto_with_retry (200 only, wait_until=load). - tests/custom-html/playwright/test_browser_smoke.py: same. - tests/n8n/test_install.py: replaced inline retry loop with goto_with_retry (200, 304). - tests/keycloak/test_install.py: goto_with_retry for admin console (200, 302, 303; 45s goto). - tests/cryptpad/test_install.py: goto_with_retry (200, 304; 60s goto, wait_until=load). - tests/lasuite-docs/test_install.py: goto_with_retry (200, 301, 302; 60s goto). Cold-verifiable: ssh cc-ci 'RECIPE=custom-html cc-ci-run runner/run_recipe_ci.py' all 5 stages PASS (including the install overlay that flaked in the deps_smoke run), deploy-count=1, head_ref=8a026066==chaos-version=8a026066 (HC1 non-vacuous). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@ -8,7 +8,7 @@ import os
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "runner"))
|
||||
from harness import generic, lifecycle # noqa: E402
|
||||
from harness import browser as harness_browser, generic, lifecycle # noqa: E402
|
||||
|
||||
|
||||
def test_serving_and_editor(live_app, meta):
|
||||
@ -21,9 +21,9 @@ def test_serving_and_editor(live_app, meta):
|
||||
|
||||
# A real browser loads the live n8n editor SPA over HTTPS.
|
||||
# n8n's boot is staged: /healthz returns 200 before / route is registered. So we may briefly
|
||||
# get 404 from /, then a 200 with the "starting up" placeholder, then the actual SPA. Poll
|
||||
# page.goto until status==200 (route registered) — Phase 1e exec_in_app pattern: bounded poll,
|
||||
# no bare sleep, raise on persistent failure.
|
||||
# get 404 from /, then a 200 with the "starting up" placeholder, then the actual SPA. The
|
||||
# centralized harness.browser.goto_with_retry helper handles both the status-mismatch retry
|
||||
# AND transient PlaywrightError (net::ERR_*) — F2-3 hardening.
|
||||
from playwright.sync_api import sync_playwright
|
||||
|
||||
url = f"https://{live_app}/"
|
||||
@ -32,29 +32,9 @@ def test_serving_and_editor(live_app, meta):
|
||||
try:
|
||||
ctx = browser.new_context(ignore_https_errors=True)
|
||||
page = ctx.new_page()
|
||||
import time
|
||||
|
||||
from playwright.sync_api import Error as PlaywrightError
|
||||
|
||||
deadline = time.time() + 120
|
||||
resp = None
|
||||
last_status = 0
|
||||
last_err = ""
|
||||
while time.time() < deadline:
|
||||
try:
|
||||
resp = page.goto(url, wait_until="domcontentloaded", timeout=30000)
|
||||
except PlaywrightError as e: # net::ERR_*, transient navigation, etc. (F2-3)
|
||||
last_err = str(e)
|
||||
resp = None
|
||||
last_status = 0
|
||||
else:
|
||||
last_status = resp.status if resp is not None else 0
|
||||
if last_status in (200, 304):
|
||||
break
|
||||
time.sleep(3)
|
||||
assert resp is not None and last_status in (200, 304), (
|
||||
f"page status {last_status} after polling — n8n route never came up "
|
||||
f"(last error: {last_err or 'none'})"
|
||||
resp = harness_browser.goto_with_retry(page, url, accept_statuses=(200, 304))
|
||||
assert resp is not None and resp.status in (200, 304), (
|
||||
f"page status {resp and resp.status}"
|
||||
)
|
||||
body = page.content().lower()
|
||||
assert "n8n" in body or "<html" in body, "no n8n content served"
|
||||
|
||||
Reference in New Issue
Block a user